Yet another opinion on LLMs · Hasufell's blog

exactly this: give an LLM a stub function with some very distinct types and a defined behavior, and it can fill that in without issues. add a few unit tests to that to actually verify it, and it is having a hard time to produce anything that’s fundamentally wrong. the coding style? from meh to horrible at times, but if prodded enough, it can clean that up too doing a refactor and now you got a bunch of simple compile errors all throughout the project? a coding agent is perfectly capable of compiling, fixing those locally, repeat. even isn’t that bad at writing sed scripts that to a lot of that mechanically (haskell has quite a big advantage here since it is nearly impossible to get this wrong and the code to still compile) so there are quite a few scenarios where you can effectively use them. you don’t even have to touch your editor to actually write out most of your actual, just stub out a structure that makes sense, mark problematic sections that need rework, point out edge cases that still need to be tested/verified, and in such a limited scope, that works perfectly well. just don’t let it off the leash, or you’ll end up with a mess that nobody (human or ai) can fix or maintain past a certain size